Staple: Complementary learners for real-time tracking
Correlation Filter-based trackers have recently achieved excellent performance, showing great robustness to challenging situations exhibiting motion blur and illumination changes. However, since the model that they learn depends strongly on the spatial layout of the tracked object, they are notoriou...
Главные авторы: | Bertinetto, L, Valmadre, J, Golodetz, S, Miksik, O, Torr, P |
---|---|
Формат: | Journal article |
Опубликовано: |
IEEE
2016
|
Схожие документы
-
Learning feed-forward one-shot learners
по: Bertinetto, L, и др.
Опубликовано: (2016) -
End-to-end representation learning for Correlation Filter based tracking
по: Valmadre, J, и др.
Опубликовано: (2017) -
Fully-convolutional Siamese networks for object tracking
по: Bertinetto, L, и др.
Опубликовано: (2016) -
The visual object tracking VOT2015 challenge results
по: Kristan, M, и др.
Опубликовано: (2016) -
Long-term tracking in the wild: a benchmark
по: Valmadre, J, и др.
Опубликовано: (2018)